GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
YONKWd
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
YONKWd
Model Tree
Qwen/Qwen3-1.7B-Base
Input Modalities
Output Modalities
Supported Functionality
This repository contains the experimental Spexcon S1 v0.4 pilot LoRA adapter. It is not the full Spexcon S1 release and should not be treated as a production-quality model.
Qwen/Qwen3-1.7B-BaseYONKWd/Spexcon-S1HuggingFaceH4/ultrachat_200kmit2000200Tesla T42.39722800254821781.3996604919433593The v0.4 goal is cleaner English-focused behavior, fewer role-template leaks, less repetition, cleaner stop behavior, and more consistent Spexcon identity compared with the v0.3 smoke-test adapter.
Load with PEFT:
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase_model = "Qwen/Qwen3-1.7B-Base"adapter = "YONKWd/Spexcon-S1-v0.4-Pilot"tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")model = PeftModel.from_pretrained(model, adapter)